UI-Vision: leaderboard
Given a desktop screenshot from one of 83 applications and a text query, the model must point at the named UI element; the score is the source's Final Avg of the Basic, Functional and Spatial settings (1,772, 1,772 and 1,935 queries per model). Unlike ScreenSpot-Pro it splits queries by how the element is described (name, function, or position relative to other elements).
Metric: Element grounding accuracy (%), Final Avg of the Basic, Functional and Spatial settings (point inside the target element's box). Source: raw.githubusercontent.com. Saturation forecast: Around 2029. 12 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Aguvis-7B | 13.7 | |
| 2 | OS-Atlas-Base-7B | 9.02 | |
| 3 | CogAgent-9B-20241220 | 8.94 | |
| 4 | Claude 3.7 Sonnet (20250219) | 8.27 | #421 |
| 5 | ShowUI-2B | 5.94 | |
| 6 | SeeClick | 5.39 | |
| 7 | MiniCPM-V-2.6 | 4.34 | #3523 |
| 8 | Qwen 2 VL 7B Instruct | 2.7 | #2594 |
| 9 | InternVL2.5-8B | 2.09 | #2401 |
| 10 | Qwen 2.5 VL 7B Instruct | 0.85 | #1893 |
| 11 | Gemini 2.0 Flash (001) | 0.3 | #727 |
| 12 | InternVL2-8B | 0.09 | #3359 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=ui-vision · How It Works · Data refreshed daily, snapshot 2026-11-17.